{"type":"ScholarlyArticle","title":"LiBOG: Lifelong Learning for Black-Box Optimizer Generation","authors":[{"name":"Jiyuan Pei","slug":"jiyuan-pei","given":"Jiyuan","family":"Pei","affiliation":""},{"name":"Yi Mei","slug":"yi-mei","given":"Yi","family":"Mei","affiliation":""},{"name":"Jialin Liu","slug":"jialin-liu","given":"Jialin","family":"Liu","affiliation":""},{"name":"Mengjie Zhang","slug":"mengjie-zhang","given":"Mengjie","family":"Zhang","affiliation":""}],"abstract":"Meta-Black-Box Optimization (MetaBBO) garners attention due to its success in automating the configuration and generation of black-box optimizers, significantly reducing the human effort required for optimizer design and discovering optimizers with higher performance than classic human-designed optimizers. However, existing MetaBBO methods conduct one-off training under the assumption that a stationary problem distribution with extensive and representative training problem samples is pre-available. This assumption is often impractical in real-world scenarios, where diverse problems following shifting distribution continually arise. Consequently, there is a pressing need for methods that can continuously learn from new problems encountered on-the-fly and progressively enhance their capabilities. In this work, we explore a novel paradigm of lifelong learning in MetaBBO and introduce LiBOG, a novel approach designed to learn from sequentially encountered problems and generate high-performance optimizers for Black-Box Optimization (BBO). LiBOG consolidates knowledge both across tasks and within tasks to mitigate catastrophic forgetting. Extensive experiments demonstrate LiBOG's effectiveness in learning to generate high-performance optimizers in a lifelong learning manner, addressing catastrophic forgetting while maintaining plasticity to learn new tasks.","doi":"10.24963/ijcai.2025/991","url":"https://ijcai.org/proceedings/2025/991","pdf":"https://ijcai.org/proceedings/2025/0991.pdf","markdown":"https://ijcai.org/proceedings/2025/991.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/991","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Search","track":"Main Track","number":991,"pages":{"first":8912,"last":8920},"keywords":["Search: S: Meta-reasoning and meta-heuristics","Search: S: Algorithm portfolios and configuration","Search: S: Search and machine learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}